Ensembled Semi Supervised Clustering Approach for High Dimensional Data

Abstract

we first propose an incremental semi-supervised clustering ensemble framework (ISSCE) that makes use of the advantage of the random subspace technique, the constraint propagation approach, the incremental ensemble member selection process, and the normalized cut algorithm to perform high dimensional data clustering. The random subspace technique is effective for handling high dimensional data, while the constraint propagation approach is useful for incorporating prior knowledge. The incremental ensemble member selection process is newly designed to remove redundant ensemble members based on a newly proposed local cost function and a global cost function, and the normalized cut algorithm is adopted to serve as the consensus function for providing more stable, robust, and accurate results.

Authors and Affiliations

M. LeelaReddy, Naveen Sai, G. Keerthi, M. Druga Kalyani

Keywords

Related Articles

Numerical Investigation on Thermal Characteristics of Air in a Square Duct Using Ribs as Vortex Generator

The numerical investigation has been carried out on one wall of square duct to study the effect of influence of ribs upon thermal characteristics and fluid flow of air in a square duct. Analysis is done by using CFD too...

Our Future: Artificial Intelligence, Expert Systems & Robots

Artificial Intelligence is the concept of computer science which deals with building computers that exhibits the intelligent behaviour like us. In other words it concern with making intelligent machines which having abi...

slugA Design Approach of Normalized Least Mean Square (NLMS) Algorithm for Low Power Implementation of Adaptive Noise Cancellation

The basic theme of our paper is to implement a new idea of noise re ducti on in the real time implementation using the concepts of adaptive filters. This method uses a “Primary I nput” cont aining corrupted sig...

Virtual Private Network Security

This research is on the implementation of Virtual Private Network (VPN). Owing to the demand at the present time to connect to internal networks from distant locations, the significant of establishing safe links across...

Harmonic Injection Technique to Reduce Harmonic

A harmonic injection technique, which reduces theline frequency harmonics of the single switch three-phase boost rectifier, has been implemented. In this method, a periodic voltage is injected in the control circuit to...

Download PDF file
  • EP ID EP23916
  • DOI http://doi.org/10.22214/ijraset.2017.4210
  • Views 295
  • Downloads 9

How To Cite

M. LeelaReddy, Naveen Sai, G. Keerthi, M. Druga Kalyani (2017). Ensembled Semi Supervised Clustering Approach for High Dimensional Data. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 5(4), -. https://europub.co.uk/articles/-A-23916